8a8f43410d
chore(docker): use nvidia base image ( #318 )
2023-05-12 17:32:40 +02:00
76a48cd365
feat(server): GPTQ quantization (step1) ( #277 )
...
Changes only the type from `bool` to `Option<Enum>` pretty much
everywhere.
- Use `Optional[str]` in Python (easier to manage than importing type
everywhere). Except for the cli to get proper validation
- Updated all models to handle gracefully new values. (Error out if
unknown value, or gptq since not implemented).
<!--
Congratulations! You've made it this far! You're not quite done yet
though.
Once merged, your PR is going to appear in the release notes with the
title you set, so make sure it's a great title that fully reflects the
extent of your awesome contribution.
Then, please replace this with a description of the change and which
issue is fixed (if applicable). Please also include relevant motivation
and context. List any dependencies (if any) that are required for this
change.
Once you're done, someone will review your PR shortly (see the section
"Who can review?" below to tag some potential reviewers). They may
suggest changes to make the code even better. If no one reviewed your PR
after a week has passed, don't hesitate to post a new comment
@-mentioning the same persons---sometimes notifications get lost.
-->
<!-- Remove if not applicable -->
Fixes # (issue)
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Did you read the [contributor
guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests ),
Pull Request section?
- [ ] Was this discussed/approved via a Github issue or the
[forum](https://discuss.huggingface.co/ )? Please add a link
to it if that's the case.
- [ ] Did you make sure to update the documentation with your changes?
Here are the
[documentation
guidelines](https://github.com/huggingface/transformers/tree/main/docs ),
and
[here are tips on formatting
docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation ).
- [ ] Did you write any new necessary tests?
## Who can review?
Anyone in the community is free to review the PR once the tests have
passed. Feel free to tag
members/contributors who may be interested in your PR.
<!-- Your PR will be replied to more quickly if you can figure out the
right person to tag with @
@OlivierDehaene OR @Narsil
-->
2023-05-12 14:46:41 +02:00
4f6d038c0b
fix(server): fix multinomial implem in Sampling
2023-05-11 13:30:38 +02:00
a6c18c39bb
feat(server): use cuda graph in logits warping ( #302 )
2023-05-10 19:08:54 +02:00
745f596c88
feat(server): use float16 ( #304 )
2023-05-10 15:51:10 +02:00
68e9d6ab33
feat(server): shard token decode ( #303 )
2023-05-10 15:48:21 +02:00
ad66f6ef9a
feat(server): optim flash causal lm decode_token ( #285 )
2023-05-09 18:26:19 +02:00
b4aa87db58
fea(server): decrease convert RAM requirements ( #286 )
2023-05-05 17:57:02 +02:00
690fc31757
fix(server): fix convert ( #284 )
2023-05-05 15:28:08 +02:00
f08343d44d
fix(server): Removes the parallelism in file convertion (during download) ( #275 )
2023-05-04 15:22:54 +02:00
85aa7e2e7b
feat(server): support hf endpoint weight layout ( #266 )
2023-05-03 11:36:24 +02:00
4096000e34
fix(server): fix typo in tokenizers decode ( #269 )
...
closes #268
2023-05-03 10:10:34 +02:00
f092ba9b22
feat(server): add watermarking tests ( #248 )
2023-04-27 19:16:35 +02:00
b9ae7e5da1
chore(server): update transformers ( #250 )
2023-04-27 09:57:41 +02:00
34bca0b8d3
fix(server): Small tidy of code from recent changes ( #251 )
...
remaining_decode_tokens was calculated twice in Seq2SeqLMBatch.filter()
2023-04-27 09:57:28 +02:00
b4cf832c40
fix(server): fix reshaping of bloom past_key_values in concatenate() ( #252 )
...
Introduced in #214
Fixes #249
2023-04-27 09:51:27 +02:00
db2b4e0754
feat(router): new healthcheck that skips the queue ( #244 )
...
Co-authored-by: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
Co-authored-by: OlivierDehaene <olivier@huggingface.co>
2023-04-26 20:23:54 +02:00
37b64a5c10
chore(server): update safetensors version ( #235 )
2023-04-25 13:50:56 +02:00
ebc74d5666
feat(router): use number of tokens in batch as input for dynamic batching ( #226 )
...
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2023-04-24 17:59:00 +02:00
98a3e0d135
chore(server): update huggingface-hub ( #227 )
2023-04-24 15:57:13 +02:00
4a7dd4085a
feat(server): reduce memory requirement ( #214 )
2023-04-24 14:15:42 +02:00
6ded76a4ae
v0.6.0 ( #222 )
2023-04-21 21:00:57 +02:00
4b460e72fb
fix(server): fix flash batch filtering ( #220 )
2023-04-21 20:26:01 +02:00
1ffea36ec2
fix(server): fix flash causal ( #219 )
2023-04-21 19:49:08 +02:00
86bca365df
fix(server): fix flash causal ( #218 )
2023-04-21 19:42:16 +02:00
afc5b999d0
fix(server): cleanup new flash past_key_values logic ( #217 )
2023-04-21 16:19:04 +02:00
db4cb5e4ed
fix(server): fix past key values logic ( #216 )
...
@njhill fyi
2023-04-21 15:59:18 +02:00
343437c7b5
feat(router): add device and dtype info ( #215 )
2023-04-21 15:36:29 +02:00
ac8c0f6fe4
feat(server): flash attention past key value optimizations ( #213 )
2023-04-21 14:57:18 +02:00
709d8936f6
feat(router): drop requests when client closes the channel ( #202 )
2023-04-20 11:07:40 +02:00
b6ee0ec7b0
feat(router): add git sha to info route ( #208 )
2023-04-19 21:36:59 +02:00
6837b2eb77
fix(docker): remove unused dependencies ( #205 )
2023-04-19 19:39:31 +02:00
5d27f5259b
fix(server): fix hf_transfer issue with private repos ( #203 )
2023-04-19 17:36:16 +02:00
a88c54bb4c
feat(server): check cuda capability when importing flash models ( #201 )
...
close #198
2023-04-19 12:52:37 +02:00
e14ae3b5e9
feat(server): support quantization for flash models ( #200 )
...
closes #197
2023-04-19 12:51:11 +02:00
7a1ba58557
fix(docker): fix docker image dependencies ( #187 )
2023-04-17 00:26:47 +02:00
53ee09c0b0
fea(dockerfile): better layer caching ( #159 )
2023-04-14 10:12:21 +02:00
64347b05ff
fix(ci): fix CVE in github-slug-action ( #174 )
2023-04-13 12:43:05 +02:00
880a76eed5
feat(server): support sharded santacoder ( #167 )
2023-04-12 17:18:08 +02:00
5fa8ae041c
feat(server): optimize decode for sane tokenizers ( #170 )
2023-04-12 12:03:10 +02:00
6f0f1d70f6
v0.5.0 ( #168 )
2023-04-11 20:32:18 +02:00
f26dfd0dc1
feat(server): support OPT models ( #55 )
...
OPT models do not all have a `tokenizer.json` file on the hub at the
moment. Can't merge for now.
2023-04-11 19:16:41 +02:00
299217c95c
feat(server): add flash attention llama ( #144 )
2023-04-11 16:38:22 +02:00
9987960062
feat(router): make router input validation optional ( #164 )
2023-04-09 20:22:27 +02:00
1883d8ecde
feat(docker): improve flash_attention caching ( #160 )
2023-04-09 19:59:16 +02:00
3f2542bb6a
fix(server): fix escape characters in stop sequence ( #155 )
2023-04-05 19:37:41 +02:00
c0aeb32583
feat(server): flash santacoder ( #153 )
2023-04-03 19:06:42 +02:00
fef1a1c381
v0.4.3 ( #152 )
2023-03-30 17:28:14 +02:00
84722f3e33
v0.4.2 ( #151 )
2023-03-30 17:10:01 +02:00
08b7e4a282
fix(server): fix flash neox rotary embeddings ( #150 )
2023-03-30 16:12:23 +02:00
610bb1f978
feat(benchmark): tui based benchmarking tool ( #149 )
2023-03-30 15:26:27 +02:00
c9bdaa8b73
feat(server): reduce mlp and attn in one op for flash neox ( #145 )
2023-03-28 16:51:41 +02:00
f000068944
feat(server): clear cache on error ( #143 )
2023-03-28 11:29:35 +02:00
8e8dd984d8
feat(server): Add mypy-protobuf ( #141 )
...
Generates .pyi files for protobuf stubs which provide strong typing
information. Very helpful for IDE auto-completion, etc.
2023-03-27 09:25:15 +02:00
462530c2b0
fix(server): Avoid using try/except to determine kind of AutoModel ( #142 )
2023-03-27 09:23:22 +02:00
ab5fd8cf93
v0.4.1 ( #140 )
2023-03-26 16:37:51 +02:00
678b2f3900
feat(server): cleanup flash neox loading ( #139 )
2023-03-26 16:37:21 +02:00
d6a93fe992
fix(server): fix flash-neox scores warping ( #137 )
2023-03-24 18:21:41 +01:00
05e9a796cc
feat(server): flash neoX ( #133 )
2023-03-24 14:02:14 +01:00
b49dbf2d88
fix(server): use server tokenizer as gt ( #128 )
2023-03-16 12:12:26 +01:00
8ad60b752f
fix(server): add position ids to neox ( #126 )
2023-03-15 13:12:49 +01:00
cbd36aa4d1
fix(server): revert gpt-neox optims ( #123 )
2023-03-13 22:57:08 +01:00
411d6247f4
v0.4.0 ( #119 )
2023-03-09 16:07:01 +01:00
c0795de2f2
fix(server): do not warp prefill logits ( #116 )
2023-03-09 13:00:10 +01:00
1a2d68250a
feat: support typical sampling ( #114 )
...
closes #112
2023-03-09 11:33:57 +01:00
941cd42e0c
fix(server): fix index out of range for watermarking ( #110 )
2023-03-08 18:29:08 +01:00
b1485e18c5
fix(server): fix galactica batch ( #106 )
...
closes #105
2023-03-07 20:05:21 +01:00
3fef90d50f
feat(clients): Python client ( #103 )
2023-03-07 18:52:22 +01:00
cd5961b5da
feat: allow local models ( #101 )
...
closes #99
2023-03-06 14:39:36 +01:00
9b205d33cc
fix(server): fix generate_stream by forcing tokens to be decoded correctly ( #100 )
2023-03-06 13:22:58 +01:00
1c19b0934e
v0.3.2 ( #97 )
2023-03-03 18:42:20 +01:00
0b6807caa4
feat(server): fix transformers commit ( #96 )
2023-03-03 17:56:27 +01:00
2d39f199ae
feat(server): update to hf_transfer==0.1.2 ( #93 )
2023-03-03 11:26:27 +01:00
9b8ea6a6c7
feat(server): add logits watermark ( #90 )
2023-03-02 12:30:41 +01:00
65e2f1624e
fix(server): fix token_is_special ( #87 )
2023-02-24 17:20:00 +01:00
0ac184ce77
feat(server): add special token bool ( #85 )
2023-02-24 15:55:57 +01:00
4b1c9720c0
v0.3.1 ( #84 )
2023-02-24 13:27:41 +01:00
44ce098c10
feat(server): pre-allocate max attention mask ( #75 )
2023-02-24 12:49:21 +01:00
78063c0569
fix(server): remove position_ids from galactica forward ( #82 )
...
closes #80
2023-02-20 19:28:57 +01:00
17bc841b1b
feat(server): enable hf-transfer ( #76 )
2023-02-18 14:04:11 +01:00
c720555adc
v0.3.0 ( #72 )
2023-02-16 17:28:29 +01:00
439fcaf810
feat(router): add prometheus metrics scrape endpoint ( #71 )
2023-02-16 17:18:53 +01:00
c5a4a1faf3
feat(server): improve download logging ( #66 )
2023-02-15 16:11:32 +01:00
0fbc691946
feat: add safetensors conversion ( #63 )
2023-02-14 13:02:16 +01:00
9af454142a
feat: add distributed tracing ( #62 )
2023-02-13 13:02:45 +01:00
1ad3250b89
fix(docker): increase shm size ( #60 )
2023-02-08 17:53:33 +01:00
c503a639b1
feat(server): support t5 ( #59 )
2023-02-07 18:25:17 +01:00
2fe5e1b30e
V0.2.1 ( #58 )
2023-02-07 15:40:25 +01:00
4acc42a605
fix(server): better handling of inference mode ( #57 )
2023-02-07 15:38:22 +01:00
20c3c5940c
feat(router): refactor API and add openAPI schemas ( #53 )
2023-02-03 12:43:37 +01:00
b1482d9048
breaking(router): modify /generate API to only return generated text ( #50 )
...
@njhill, @yk FYI
generated_text was concatenated to the user prompt for legacy reason. We
want to remove this behaviour as we don't think it is useful and even
detrimonial to usability.
We also remove the unused Vec.
2023-02-02 15:02:04 +01:00
df227ac20d
fix(server): allow greedy repetition penalty ( #51 )
2023-02-02 10:34:35 +01:00
775115e3a5
feat(server): allow the server to use a local weight cache ( #49 )
2023-02-01 16:22:10 +01:00
313194f6d7
feat(server): support repetition penalty ( #47 )
2023-02-01 15:58:42 +01:00
2ad895a6cc
feat(server): allow gpt-neox models with odd vocab sizes to be sharded ( #48 )
2023-02-01 14:43:59 +01:00
f830706b21
feat(server): Support GPT-Neox ( #39 )
2023-01-31 18:53:56 +01:00
c6e8b9442b
fix(server): fix quantization for sharded models ( #45 )
2023-01-31 17:40:38 +01:00
017a2a8c2f
feat: Add token streaming using ServerSideEvents support ( #41 )
2023-01-31 17:04:00 +01:00
54fec93193
fix(server): fix seeding with multiple shards ( #44 )
2023-01-31 16:01:15 +01:00
03bdf18290
fix(server): fix seeding on gpu ( #42 )
2023-01-31 14:30:33 +01:00
4f9ac67cfa
Revert "feat: Add token streaming using ServerSideEvents support" ( #40 )
...
Reverts huggingface/text-generation-inference#36
2023-01-31 14:21:51 +01:00
7fbfbb0dc5
feat: Add token streaming using ServerSideEvents support ( #36 )
...
Add token streaming using ServerSideEvents (SSE).
The signature of the SSE events is:
```rust
struct Details {
finish_reason: String,
generated_tokens: u32,
seed: Option<u64>,
}
struct StreamResponse {
token: Token,
generated_text: Option<String>,
details: Option<Details>,
}
struct ErrorResponse {
error: String,
}
```
2023-01-31 11:49:43 +01:00
cd298bc5e5
feat: Support sampling seeding ( #37 )
...
Co-authored-by: Yannic Kilcher <yk@users.noreply.github.com>
2023-01-30 15:36:16 +01:00
ce960be0a5
feat(bloom): use torch.nn.Linear and torch.nn.GELU ( #33 )
2023-01-26 15:33:45 +01:00
13e7044ab7
fix(dockerfile): fix docker build ( #32 )
2023-01-24 19:52:39 +01:00
1f570d181f
fix(server): Fix position ids ( #28 )
2023-01-20 15:35:22 +01:00
15511edc01
feat(server): Support SantaCoder ( #26 )
2023-01-20 12:24:39 +01:00
e6d3eb5d5d
fix(server): Minor refactorization using new_zeros ( #24 )
...
- Fix some type hints, in particular base tokenizer class
- Make use of `tensor.new_zero/empty` methods
- Simplify env var string parsing in launcher
2023-01-17 09:10:22 +01:00
fcc2c5fcbf
feat(launcher): Log server stdout ( #19 )
...
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2023-01-05 12:01:23 +01:00
b94f30215f
fix(server): Use cleanup_tokenization_spaces=False for lossless decoding ( #13 )
...
Fixes #12 in the easiest way I could think of.
2023-01-03 11:07:05 +01:00
686cc66717
fix(server): Check for device type correctly when determining initial padding ( #16 )
...
AFAIK there is no torch device type called "gpu".
2022-12-30 19:30:42 +01:00
611e21cb13
fix(server): Fix stop sequences ( #11 )
2022-12-16 16:03:39 +01:00
32a253063d
feat: Return logprobs ( #8 )
2022-12-15 17:03:56 +01:00
718096f695
feat: Support stop sequences ( #7 )
2022-12-12 18:25:22 +01:00
042180d88f
fix(server): Only pad to multiple of 8 on GPUs
2022-12-08 19:37:37 +01:00
a2985036aa
feat(server): Add model tests ( #6 )
2022-12-08 18:49:33 +01:00
31d76e238d
fix(batching): Avoid theoretical hang in batcher loop ( #5 )
...
- Avoid theoretical hang in batcher loop
- Avoid a couple of clones in the router generate method
- Keep attention mask tensors as integers
- Remove num_heads attribute
Co-authored-by: OlivierDehaene <Olivier.dehaene@gmail.com>
2022-12-05 10:10:59 +01:00
daa1d81d5e
feat(server): Support Galactica ( #4 )
2022-12-01 19:31:54 +01:00
dccd5c2b1a
feat(server): Clarify CausalLMBatch concatenate method
2022-11-09 18:24:07 +01:00
fa43fb71be
fix(server): Fix Transformers fork version
2022-11-08 17:42:38 +01:00
4236e41b0d
feat(server): Improved doc
2022-11-07 12:53:56 +01:00
427d7cc444
feat(server): Support AutoModelForSeq2SeqLM
2022-11-04 18:03:04 +01:00
c5665f5c8b
feat(server): Support generic AutoModelForCausalLM
2022-11-04 14:22:47 +01:00
755fc0e403
fix(models): Revert buggy support for AutoModel
2022-11-03 16:07:54 +01:00
b3b7ea0d74
feat: Use json formatter by default in docker image
2022-11-02 17:29:56 +01:00
3cf6368c77
feat(server): Support all AutoModelForCausalLM on a best effort basis
2022-10-28 19:24:00 +02:00
09674e6df9
feat(server): Support bitsandbytes
2022-10-27 14:25:29 +02:00
c8ce9b2515
feat(server): Use safetensors
...
Co-authored-by: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
2022-10-22 20:00:15 +02:00
f16f2f5ae1
v0.1.0
2022-10-20 19:14:44 +02:00
5e5d8766a2
feat: Improve error handling
2022-10-17 14:59:00 +02:00
bcb53903b8
feat: Add AML deployment
2022-10-15 20:21:50 +02:00
bf99afe916
feat: Docker image
2022-10-14 15:56:21 +02:00
4c693e6524
Refactored gRPC interface
...
Added validation logic
2022-10-11 16:50:54 +02:00
1d986983d5
fix: cleanup
2022-10-08 12:34:25 +02:00
295831a481
Init
2022-10-08 12:30:12 +02:00
OlivierDehaene